{"list":"other","total":71,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131},{"id":"2001.09239","title":"Multi-task self-supervised learning for Robust Speech Recognition","created":"2020-01-25","cited_by_count":130},{"id":"2009.00909","title":"A Survey on Negative Transfer","created":"2020-09-02","cited_by_count":122},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2406.15479","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","created":"2024-06-17","cited_by_count":116},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81},{"id":"2310.12808","title":"Model Merging by Uncertainty-Based Gradient Matching","created":"2023-10-19","cited_by_count":77},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65},{"id":"2109.09138","title":"Multi-Task Learning in Natural Language Processing: An Overview","created":"2021-09-19","cited_by_count":62},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2007.06889","title":"Knowledge Distillation for Multi-task Learning","created":"2020-07-14","cited_by_count":51},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51},{"id":"2003.14058","title":"MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning","created":"2020-03-31","cited_by_count":50},{"id":"2304.14381","title":"$\\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation","created":"2023-04-27","cited_by_count":40},{"id":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34},{"id":"2403.01753","title":"Training-Free Pretrained Model Merging","created":"2024-03-04","cited_by_count":32},{"id":"2211.15055","title":"AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning","created":"2022-11-28","cited_by_count":31},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20},{"id":"2307.08122","title":"Tangent Transformers for Composition, Privacy and Removal","created":"2023-07-16","cited_by_count":13},{"id":"1807.11698","title":"Rank and Rate: Multi-task Learning for Recommender Systems","created":"2018-07-31","cited_by_count":12}],"next_cursor":null}